Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning.
Peter VamplewCameron FoaleConor F. HayesPatrick MannionEnda HowleyRichard DazeleyScott JohnsonJohan KällströmGabriel de Oliveira RamosRoxana RadulescuWillem RöpkeDiederik M. RoijersPublished in: AAMAS (2024)
Keyphrases
- reinforcement learning
- multi objective
- function approximation
- state space
- evolutionary algorithm
- markov decision processes
- robotic control
- reinforcement learning algorithms
- optimal control
- particle swarm optimization
- learning algorithm
- transfer learning
- multi objective optimization
- temporal difference
- dynamic programming
- temporal difference learning
- optimal policy
- neural network
- optimization algorithm
- multiple objectives
- model free
- action selection